Evaluating Effectiveness of Crop Yield Prediction using Machine Learning: A Comparative Analysis

Precise forecasting of crop yields plays a pivotal role in advancing sustainable agricultural practices and ensuring global food security. This review paper presents a systematic evaluation of contemporary studies utilizing machine learning (ML) and deep learning (DL) techniques for yield prediction. The analysis encompasses investigations employing multi-modal data inputs, ranging from remote sensing data and soil characteristics to meteorological and climatic variables. The study critically examines the performance of various predictive models, including traditional machine learning approaches such as Linear Regression (LR), Support Vector Machines (SVM), Random Forest (RF), and Extra Trees (ET) as well as advanced neural network architectures such as Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), Deep Neural Networks (DNN), and Long Short- Term Memory networks (LSTM). Furthermore, the paper highlights current limitations in the field and suggests potential avenues for future research to enhance prediction accuracy and applicability.